Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1365 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.4770. Min Act: -0.0001

Data Index: 1567735 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1639451 (Python Code)

Max Activating Token Index: 508

Text #2

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3315. Min Act: -0.0001

Data Index: 1562313 (Python Code)

Max Activating Token Index: 403

Text #3

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.3481. Min Act: -0.0001

Data Index: 1457650 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2863. Min Act: -0.0001

Data Index: 1591154 (Python Code)

Max Activating Token Index: 522

Text #5

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1464398 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1941. Min Act: -0.0001

Data Index: 1511836 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2246. Min Act: -0.0001

Data Index: 1643595 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1443. Min Act: -0.0001

Data Index: 1591551 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1831. Min Act: -0.0001

Data Index: 1485385 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1797. Min Act: -0.0001

Data Index: 1452304 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1361. Min Act: -0.0001

Data Index: 1537055 (Python Code)

Max Activating Token Index: 610

Text #12

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1261. Min Act: -0.0001

Data Index: 1360887 (Python Code)

Max Activating Token Index: 667

Text #13

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.2000. Min Act: -0.0001

Data Index: 1396455 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1505857 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1941. Min Act: -0.0001

Data Index: 1636191 (Python Code)

Max Activating Token Index: 495

Text #16

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1454. Min Act: -0.0001

Data Index: 1430565 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1757. Min Act: -0.0001

Data Index: 1372804 (Python Code)

Max Activating Token Index: 380

Text #18

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1734. Min Act: -0.0001

Data Index: 1621910 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 1.4770. Min Range: -1.4770

Max Act: 1.1098. Min Act: -0.0001

Data Index: 1407959 (Python Code)

Max Activating Token Index: 388